Write a Blog >>
SPLASH 2017
Sun 22 - Fri 27 October 2017 Vancouver, Canada
Wed 25 Oct 2017 16:14 - 16:37 at Regency A - Synthesis Chair(s): Jonathan Edwards

This paper presents a new technique for automatically synthesizing SQL queries from natural language (NL). At the core of our technique is a new NL-based program synthesis methodology that combines semantic parsing techniques from the NLP community with type-directed program synthesis and automated program repair. Starting with a program sketch obtained using standard parsing techniques, our approach involves an iterative refinement loop that alternates between probabilistic type inhabitation and automated sketch repair. We use the proposed idea to build an end-to-end system called SQLIZER that can synthesize SQL queries from natural language. Our method is fully automated, works for any database without requiring additional customization, and does not require users to know the underlying database schema. We evaluate our approach on over 450 natural language queries concerning three different databases, namely MAS, IMDB, and YELP. Our experiments show that the desired query is ranked within the top 5 candidates in close to 90% of the cases and that SQLIZER outperforms NALIR, a state-of-the-art tool that won a best paper award at VLDB'14.

Wed 25 Oct

splash-2017-OOPSLA
15:30 - 17:22: OOPSLA - Synthesis at Regency A
Chair(s): Jonathan Edwards
splash-2017-OOPSLA150893820000015:30 - 15:52
Talk
Venkatesh SrinivasanUniversity of Wisconsin - Madison, Ara VartanianUniversity of Wisconsin-Madison, USA, Thomas RepsUniversity of Wisconsin - Madison and GrammaTech, Inc.
DOI
splash-2017-OOPSLA150893954400015:52 - 16:14
Talk
Xinyu WangUT Austin, Isil DilligUT Austin, Rishabh SinghMicrosoft Research
DOI
splash-2017-OOPSLA150894088800016:14 - 16:37
Talk
Navid YaghmazadehUniversity of Texas, Austin, Yuepeng WangUniversity of Texas at Austin, Isil DilligUT Austin, Thomas Dillig
DOI
splash-2017-OOPSLA150894223200016:37 - 16:59
Talk
Mark SantolucitoYale University, Ennan ZhaiYale University, USA, Rahul DhodapkarMongoDB, USA, Aaron ShimMicrosoft, USA, Ruzica PiskacYale University
DOI
splash-2017-OOPSLA150894357600016:59 - 17:22
Talk
Xiaokang QiuPurdue University, Armando Solar-LezamaMIT CSAIL
DOI